Sol in the shade: benchmarking Opus 4.6 and GPT-5.6 Sol for finding zero-days
中文摘要
测试 Opus 4.6 和 GPT-5.6 Sol 在大型开源项目中寻找零日漏洞的能力。
English Summary
Benchmarking Opus 4.6 and GPT-5.6 Sol's ability to find zero-day vulnerabilities in a large open-source project.
Original Excerpt
I pointed Opus 4.6 and GPT-5.6 Sol at a big, hardened open source project and told them to hunt for zero-days. Continue reading on Medium »